© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 2422
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific brain region called the striatum

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemical compounds and substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haz
    -0.64
     Wendy
    -0.62
     failings
    -0.60
     Rick
    -0.60
    opoly
    -0.60
     unsc
    -0.60
     beers
    -0.59
     Mahjong
    -0.58
     Ran
    -0.58
     Shining
    -0.57
    POSITIVE LOGITS
    atum
    3.51
    atin
    2.42
    atus
    2.29
    ata
    1.51
    atem
    1.38
    atu
    1.36
    aters
    1.27
    atis
    1.27
    ato
    1.26
    atoon
    1.21
    Activations Density 0.008%

    No Known Activations